Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.8877. Min Act: -0.1700
Data Index: 591426 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.8877. Min Act: -0.1700
Data Index: 1609157 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.8020. Min Act: -0.1700
Data Index: 4485782 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7934. Min Act: -0.1700
Data Index: 4696674 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7848. Min Act: -0.1700
Data Index: 2648836 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7761. Min Act: -0.1700
Data Index: 3883565 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7761. Min Act: -0.1700
Data Index: 6349157 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7589. Min Act: -0.1700
Data Index: 2980391 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7675. Min Act: -0.1700
Data Index: 7988600 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7675. Min Act: -0.1700
Data Index: 3185178 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7503. Min Act: -0.1700
Data Index: 4602705 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 1917149 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7330. Min Act: -0.1700
Data Index: 5946408 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 172296 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 264686 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 4311151 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 793845 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 6151461 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 5135734 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8877. Min Range: -1.8877
Max Act: 1.7416. Min Act: -0.1700
Data Index: 3973862 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19